AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Embedding Propagation: Smoother Manifold for Few-Shot Classification

Pau Rodríguez, Issam Laradji, Alexandre Drouin, Alexandre Lacoste

ECCV 2020 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Fine-grained and cross-domain few-shot baselines · 233 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add embedding propagation to label propagation (ablation)EPNet · miniImageNet 1-shot (Conv-4)accuracy (%): 53.40 -> 55.75Improved
add embedding propagation alone (prototypical classifier) (ablation)EPNet · miniImageNet 1-shot (Conv-4)accuracy (%): 49.57 -> 52.83Improved
add label propagation to embedding propagation (ablation)EPNet · miniImageNet 1-shot (Conv-4)accuracy (%): 52.83 -> 55.75Improved
add episodic fine-tuning (ablation)EPNet · miniImageNet 1-shot (Conv-4)accuracy (%): 49.57 -> 54.29Improved
add rotation loss (ablation)EPNet · miniImageNet 1-shot (Conv-4)accuracy (%): 49.57 -> 50.83Improved
add embedding propagation on top of fine-tuning, rotation loss and LP (ablation)EPNet · miniImageNet 1-shot (Conv-4)accuracy (%): 57.35 -> 58.85Improved
add embedding propagation (EPNet vs -Net) (ablation)EPNet with WRN-28-10 · miniImageNet 1-shotaccuracy (%): 65.98 -> 70.74Improved
add embedding propagation (EPNet vs -Net) (ablation)EPNet with ResNet-12 · miniImageNet 5-shotaccuracy (%): 81.28 -> 81.06No clear effect
add embedding propagation (EPNet vs -Net) (ablation)EPNet with Conv-4 · miniImageNet 5-shotaccuracy (%): 72.57 -> 72.95No clear effect
add embedding propagation to wDAE-GNNwDAE-GNN · Imagenet-FS novel classes K=1 (top-5)accuracy (%): 48.00 -> 50.07Improved
add 100 unlabeled samples (semi-supervised)EPNet with ResNet-12 · miniImageNet 1-shotaccuracy (%): 66.50 -> 75.36Improved
remove off-diagonal of propagator (keep diagonal only) (ablation)EPNet with ResNet-12 pre-training · miniImageNet 5-shotaccuracy (%): 73.80 -> 75.95Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy